Publications by authors named "Qichen Zheng"
Dynamic neural networks can greatly reduce computation redundancy without compromising accuracy by adapting their structures based on the input. In this paper, we explore the robustness of dynamic neural networks against energy-oriented attacks targeted at reducing their efficiency. Specifically, we attack dynamic models with our novel algorithm GradMDM.
View Article and Find Full Text PDFResults: This study developed mole detection and segmentation software DiaMole using mobile phone images. DiaMole utilized multiple deep learning algorithms for the object detection problem and mole segmentation problem. An object detection algorithm generated a rectangle tightly surrounding a mole in the mobile phone image.
View Article and Find Full Text PDFArticle Synopsis
- - The study focused on the prevalence of thalassemia and its genetic variations among children in Chongqing, China, revealing a total carrier frequency of 7.76%.
- - Among the carriers, 5.20% had α-thalassemia, 1.99% had β-thalassemia, and 0.57% had abnormal hemoglobin variants, with novel mutations identified for the first time in the Chinese population.
- - The findings indicate a significant risk for α- and β-thalassemia in Chongqing, providing valuable data for genetic counseling and prevention strategies in the region.